Claude Opus 5.5
Claude Opus 5.5 is Anthropic's flagship model for agentic coding, computer use, complex knowledge work, and long-running tasks, with improved efficiency and more natural communication.
- Reasoning
- Vision
- Native PDF input
- Tool Calling
- Structured Output
Added Sep 22, 2026
Pricing
Auto routing · per 1M tokens- Input
- $4.00
- Output
- $20.00
- Cache read
- $0.20
Specifications
- Context window
- 1M
- Max output
- 128K
- Avg output (7d)
- 2.8K tokens
- Longer than 97% of models
Benchmarks
Benchmarks
Sourced from Artificial Analysis.
Intelligence Index
53.6
Agentic work
AutomationBench-AA
Workflow automation with guardrail penalties
63.2%
Better than 91% of models compared
AutomationBench-AA Tasks Completed
Fully completed workflows without guardrail violations
41.2%
Better than 87% of models compared
Harvey LAB-AA
Legal agentic work criterion pass rate
90.9%
Better than 62% of models compared
AA-Briefcase
Agentic knowledge work (Elo)
1689 Elo
Better than 98% of models compared
GDPval-AA v2
Economically valuable tasks (Elo)
1707 Elo
Better than 96% of models compared
Document reasoning
GDP.pdf
Professional PDF reasoning: all-pass rate
28.8%
Better than 95% of models compared
AA-LCR v1.1
Long context reasoning with updated grading
82.7%
Better than 94% of models compared
MLCR-AA
Medical long-context reasoning
66.7%
Better than 97% of models compared
Reasoning
HLE
Humanity's Last Exam
55.6%
Better than 99% of models compared
Coding
Terminal-Bench v4.0
Practical coding and terminal tasks
56.6%
Better than 96% of models compared
SciCode
Python programming for scientific computing
60.4%
Better than 96% of models compared
Legacy benchmarks
AA-LCR (unversioned / legacy)
Long context reasoning evaluation
82.7%
Better than 94% of models compared
Last updated Oct 14, 2026
Artificial AnalysisProviders
Auto routing is available for this model. Explicit provider selection is not available.
Loading provider options…